Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 1918 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 1.2088. Min Range: -1.2088

Max Act: 1.2088. Min Act: -0.0000

Data Index: 1419494 (Python Code)

Max Activating Token Index: 205

Text #1

Max Range: 1.2088. Min Range: -1.2088

Max Act: 1.0420. Min Act: -0.0000

Data Index: 1232634 (C4 (Web Text))

Max Activating Token Index: 248

Text #2

Max Range: 1.2088. Min Range: -1.2088

Max Act: 0.9582. Min Act: -0.0000

Data Index: 1631360 (Python Code)

Max Activating Token Index: 792

Text #3

Max Range: 1.2088. Min Range: -1.2088

Max Act: 0.8893. Min Act: -0.0000

Data Index: 1606066 (Python Code)

Max Activating Token Index: 763

Text #4

Max Range: 1.2088. Min Range: -1.2088

Max Act: 1.0268. Min Act: -0.0000

Data Index: 259248 (C4 (Web Text))

Max Activating Token Index: 531

Text #5

Max Range: 1.2088. Min Range: -1.2088

Max Act: 0.9923. Min Act: -0.0000

Data Index: 39252 (C4 (Web Text))

Max Activating Token Index: 992

Text #6

Max Range: 1.2088. Min Range: -1.2088

Max Act: 1.1228. Min Act: -0.0000

Data Index: 1434794 (Python Code)

Max Activating Token Index: 907

Text #7

Max Range: 1.2088. Min Range: -1.2088

Max Act: 0.9592. Min Act: -0.0000

Data Index: 1419140 (Python Code)

Max Activating Token Index: 740

Text #8

Max Range: 1.2088. Min Range: -1.2088

Max Act: 0.9274. Min Act: -0.0000

Data Index: 425135 (C4 (Web Text))

Max Activating Token Index: 188

Text #9

Max Range: 1.2088. Min Range: -1.2088

Max Act: 0.9623. Min Act: -0.0000

Data Index: 135520 (C4 (Web Text))

Max Activating Token Index: 440

Text #10

Max Range: 1.2088. Min Range: -1.2088

Max Act: 0.8890. Min Act: -0.0000

Data Index: 1437305 (Python Code)

Max Activating Token Index: 330

Text #11

Max Range: 1.2088. Min Range: -1.2088

Max Act: 0.8857. Min Act: -0.0000

Data Index: 1425261 (Python Code)

Max Activating Token Index: 757

Text #12

Max Range: 1.2088. Min Range: -1.2088

Max Act: 0.9364. Min Act: -0.0000

Data Index: 1446067 (Python Code)

Max Activating Token Index: 799

Text #13

Max Range: 1.2088. Min Range: -1.2088

Max Act: 0.8768. Min Act: -0.0000

Data Index: 374955 (C4 (Web Text))

Max Activating Token Index: 886

Text #14

Max Range: 1.2088. Min Range: -1.2088

Max Act: 0.9308. Min Act: -0.0000

Data Index: 811132 (C4 (Web Text))

Max Activating Token Index: 326

Text #15

Max Range: 1.2088. Min Range: -1.2088

Max Act: 0.8948. Min Act: -0.0000

Data Index: 1613506 (Python Code)

Max Activating Token Index: 256

Text #16

Max Range: 1.2088. Min Range: -1.2088

Max Act: 0.8606. Min Act: -0.0000

Data Index: 1636059 (Python Code)

Max Activating Token Index: 544

Text #17

Max Range: 1.2088. Min Range: -1.2088

Max Act: 0.8783. Min Act: -0.0000

Data Index: 368796 (C4 (Web Text))

Max Activating Token Index: 977

Text #18

Max Range: 1.2088. Min Range: -1.2088

Max Act: 0.8668. Min Act: -0.0000

Data Index: 1221781 (C4 (Web Text))

Max Activating Token Index: 787

Text #19

Max Range: 1.2088. Min Range: -1.2088

Max Act: 0.8386. Min Act: -0.0000

Data Index: 988503 (C4 (Web Text))

Max Activating Token Index: 192